Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Mitigating LLM biases toward spurious social contexts using direct preference optimization
Hyunji Nam, Dorottya Demszky
LLMs are increasingly used for high-stakes decision-making, yet their sensitivity to spurious context can introduce harmful biases. This is a critical concern when models are deplo…
cs.AI2024
Predicting Long Term Sequential Policy Value Using Softer Surrogates
Hyunji Nam, Allen Nie, Ge Gao +2
Off-policy policy evaluation (OPE) estimates the outcome of a new policy using historical data collected from a different policy. However, existing OPE methods cannot handle cases…